Extending Processing Capacity of Server

1. A method of extending processing capacity of a server side, comprising: deciding a job to be offloaded from the server side, wherein the deciding a job to be offloaded from the server side comprises determining a current load level of the server side and appointing a job to be offloaded from the server side, in response to deciding that the current load level is to exceed or already exceeds a threshold load level; allocating two or more tasks to one or more clients based on attributes of the one or more clients wherein attributes of the clients include the response time of the clients, confidence degree of the clients, routing condition from the clients to the server side; allocating the two or more tasks to one or more clients in response to http requests transmitted from the one or more clients; and receiving, from the http requests transmitted from the one or more clients, responses of the one or more clients to the two or more tasks.

2. The method according to claim 1 , further comprising: selecting the one or more clients for executing the two or more tasks.

3. The method according to claim 1 , wherein allocating the two or more tasks to the one or more clients comprises: transmitting to the one or more clients task description and to-be-processed data corresponding to the two or more tasks, in response to the one or more clients logging onto the server side.

4. The method according to claim 3 , wherein the task description comprises one or more of: an input data description, an output data description, and a processing algorithm or its description.

5. The method according to claim 1 , wherein partitioning the job into two or more tasks is performed based on a predetermined rule relating to at least one of: computational load of the job, priority level of the job, confidentiality of the job, and task granularity.

6. The method according to claim 5 , wherein the task granularity is dynamically set based on client experience in executing previous tasks.

7. The method according to claim 1 , further comprising: generating a processing result of at least one part of the job based on responses of the one or more clients to the two or more tasks.

8. The method according to claim 7 , wherein the generating a processing result of at least one part of the job further comprises: obtaining confidence degree of responses from the one or more clients; and providing a processing result of at least one part of the job based on the confidence degree.

9. An apparatus for extending processing capacity of a server side, comprising: deciding means configured for deciding a job to be offloaded from the server side by determining a current load level of the server side and appointing a job to be offloaded from the server side, in response to deciding that the current load level is to exceed or already exceeds a threshold load level; partitioning means configured for partitioning the job into two or more tasks, wherein at least two of the two or more tasks have different granularities; allocating means configured for allocating the two or more tasks to one or more clients in response to http requests transmitted from the one or more clients, the allocating based on attributes of the one or more clients wherein attributes of the clients include the response time of the clients, confidence degree of the clients, routing condition from the clients to the server side; and receiving means configured for receiving, from the http requests transmitted from the one or more clients, responses of the one or more clients to the two or more tasks.

10. The apparatus according to claim 9 , further comprising: selecting means configured for selecting the one or more clients for executing the two or more tasks.

11. The apparatus according to claim 9 , wherein the allocating means comprises: transmitting means configured for transmitting to the one or more clients task description and to-be-processed data corresponding to the two or more tasks, in response to the one or more clients logging onto the server side.

12. The apparatus according to claim 11 , wherein the task description comprises one or more of: input data description, output data description, and processing algorithm or its description.

13. The apparatus according to claim 9 to, wherein the partitioning means is operated based on a predetermined rule relating to at least one of: computational load of the job, priority level of the job, confidentiality of the job, and task granularity.

14. The apparatus according to claim 13 , wherein the task granularity may be dynamically set based on client experience in executing previous tasks.

15. The apparatus according to claim 9 , further comprising: generating means configured for generating a processing result of at least one part of the job based on responses of the one or more clients to the two or more tasks.

16. The apparatus according to claim 15 , wherein the generating means further comprises: obtaining means configured for obtaining confidence degree of responses from the one or more clients; and providing means configured for providing a processing result of at least one part of the job based on the confidence degree.